• Journal of Broadcast Engineering
• /
• v.24 no.7
• /
• pp.1266-1275
• /
• 2019

With increasing criminal rates and number of CCTVs, much attention has been paid to intelligent surveillance system on the horizon. Object detection and tracking algorithms have been developed to reduce false alarms and accurately help security agents immediately response to undesirable changes in video clips such as crimes and accidents. Many studies have proposed a variety of algorithms to improve accuracy of detecting and tracking objects outside tunnels. The proposed methods might not work well in a tunnel because of low illuminance significantly susceptible to tail and warning lights of driving vehicles. The detection performance has rarely been tested against the tunnel environment. This study investigated a feasibility of object detection and tracking in an actual tunnel environment by utilizing YOLOv3 and Kernelized Correlation Filter. We tested 40 actual video clips to differentiate pedestrians and motorcycles to evaluate the performance of our algorithm. The experimental results showed significant difference in detection between pedestrians and motorcycles without false positive rates. Our findings are expected to provide a stepping stone of developing efficient detection algorithms suitable for tunnel environment and encouraging other researchers to glean reliable tracking data for smarter and safer City.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.379-387
• /
• 2015

In recent years, copyright violations from illegal copying and distribution of e-comic contents have become an important issue. Fingerprinting techniques have been emerged to provide a fast and reliable identification method of identifying e-comic contents. When illegally scanned or camera captured comic contents are distributed, they suffer from distortions. So the fingerprint differs from the original version. This paper presents a restoration framework for correcting geometric distortions in distorted comics to improve the comic content identification.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.83-86
• /
• 2012

본 논문에서는 다양한 변이 추정 방식 중 영역기반(Area-based) 알고리듬과 특정기반(Feature-based) 알고리듬을 결합한 하이브리드(Hybrid) 변이추정 알고리듬을 제안한다. 제안하는 알고리듬은 Features from Accelerated Segment Test(FAST) 코너 점 추출기[2]를 이용하여 좌, 우 영상 각각의 특징 점을 추출한 후, 특징 점들의 정보를 이용한 스테레오 정함을 통해 신뢰도 높은 초기 변이지도(Disparity map)를 생생하게 된다. 그러나 생성된 초기 변이지도는 조밀하지 못하므로, 조밀한 변이 지도를 획득하기 위해 특징점이 추출된 영역에 대해서는 추정된 초기 변이 값을 이웃 픽셀과의 색 유사도를 고려하여 전파시키고 특징 점이 추출되지 않은 영역에 대해서는 이진 윈도우(Binary window)를 활용한 영역기반 변이추정 알고리듬[1]을 이용하여 변이 값을 추정한다. 이를 통해, 제안 알고리듬은 특징 기반 알고리듬에서 발생할 수 있는 보간법 문제를 해결함과 동시에 신뢰도가 높은 초기 변이지도를 사용함으로써, 영역 기반 알고리듬의 정합 오차를 줄여 신뢰도 높은 변이지도를 생생할 수 있다. 실험 결과 추정된 초기 변이지도는 ground truth와 비교 시 약 99%이상의 정확도를 보이며, 특징 점이 추출된 영역에서 기존의 영역기반 알고리듬보다 더 정확한 변이 값이 추정되었음을 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.84-85
• /
• 2015

자막방송은 지상파 방송 수신을 통해 시청 가능한 자막 서비스를 의미하며, 현재 모든 지상파 방송 프로그램에 대해 자막방송이 제공되고 있다. 자막방송을 위한 자막 데이터는 일반적으로 속기를 통해 입력되며, 방송에서 속기를 통해 작성된 자막 데이터는 파일로 저장되어 해당 방송 프로그램에 대한 메타데이터로 활용되거나, 동일한 프로그램이 재방송으로 편성될 경우의 자막방송에 활용될 수 있다. 하지만 재방송의 경우 편집으로 인해 본방송과 내용상의 차이가 발생할 수 있으므로 편집이 발생한 부분을 포착하여 자막 데이터에도 동일한 편집을 적용한 후에 자막방송으로 활용되어야 한다. 따라서 재방송 송출에 기존 자막파일이 활용될 경우 반드시 전처리를 통해 자막과 영상의 내용을 일치시키는 과정이 필요하다. 그러나 방송 현장의 재방송 편성/송출 워크플로우에서는 자막 전처리를 위해 필요한 정보들이 갖춰지지 않는 예외적인 경우가 종종 발생하기 때문에 이를 해결하기 위한 방법이 필요하다. 이에 본 논문에서는 방송 현업의 재방송 편성/송출 워크플로우에서 파일기반 자막송출 기능을 안정적으로 사용하기 위해 자막 전처리 과정에서 발생할 수 있는 오류들에 대한 대처방법을 설명하고, 그 방법을 구현한 시스템을 소개한다.

• Journal of Broadcast Engineering
• /
• v.8 no.2
• /
• pp.153-162
• /
• 2003

This paper describes a structure of adaptive equalizer to improve reception performance of ATSC digital television (DTV) for 8-VSB receivers. There are many strong and dynamic echoes affecting reliable reception of DTV signal. Conventional DFE based least mean square (LMS) algorithm is readily implemented and has good Performance. There are still problems to be solved, however, in handling strong echoes and indoor reception. In this paper, structure of adaptive equalizer to mitigate these Problems in strong multipath interference conditions and indoor reception environment is first presented. Methods to reduce error propagation effects on DFE and initialization scheme of filter coefficients for fast convergence are then introduced. Computer simulation results prove that an adaptive equalizer with proposed design methods can combat with Brazil Ensemble and the Threshold of Visibility(TOV) is improved.

• Journal of Broadcast Engineering
• /
• v.12 no.6
• /
• pp.641-648
• /
• 2007

The decoding structure of up-to-date ATSC DTV receivers is well optimized, and it seems that 14.6 dB is the unbreakable minimum SNR in the AWGN channel. But the SNR satisfying the Shannon capacity of DTV receivers is 11.76 dB, So, the SNR gab between the 14.6 dB and the 11.76 dB is about 2.8 dB. In order to approach the Shannon capacity we propose a recursive trellis decoder which uses reliable feedback data obtained by an RS decoder. The performance enhancement of about 0.8 dB can be achieved in case of the AWGN channel.

• The KIPS Transactions:PartC
• /
• v.9C no.2
• /
• pp.235-246
• /
• 2002

While the Internet is suffering from the massive data such as video stream, IP multicast can ease the load of the Internet by enabling one copy of digital information to be received by multiple computers simultaneously. But If multicast is based on UDP, packets are delivered using a best-effort Policy without any reliability, congestion control or flow control. Multicast group members can join or leave a multicast group at will, and multicast uses broadcast mechanism, it's very hard to keep security from unauthorized members. In this paper, we introduce a new reliable multicast protocol TRDMF proper for one-to-many multicast model with reliability, flow control, congestion control and key management.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.1
• /
• pp.33-41
• /
• 2009

Network industry is complex combined with various fields of industry, such as communication, broadcast, construction, and home appliances. Moreover, it's fairly lucrative since the growth industry makes lots of added values, interacting with the others.The network industry, usually called 'Ubiquitous', connects some home appliances and makes an integrated system that you can use them with whenever and wherever. A demand for network security, however, has skyrocketed due to the relatively low safety. It's been expected that the market of home security is going to be grown up nearly 30 percent every year. Recently, analog surveilance cameras have been replaced with digital ones, and they will be providing stronger security services taking advantage of mutual interaction with related industies. In this paper, a mobile monitoring system for home security is proposed, which makes it possible to supervise all home appliances wherever you're, using the conventional wired/wireless network infra.

• Journal of Astronomy and Space Sciences
• /
• v.28 no.1
• /
• pp.71-77
• /
• 2011

Ionospheric error modeling is necessary to create reliable global navigation satellite system (GNSS) signals using a GNSS simulator. In this paper we developed algorithms to generate Klobuchar coefficients ${\alpha}_n$, ${\beta}_n$ (n = 1, 2, 3, 4) for a GNSS simulator and verified accuracy of the algorithm. The eight Klobuchar coefficients were extracted from three years of global positioning system broadcast (BRDC) messages provided by International GNSS service from 2006 through 2008 and were fitted with Fourier series. The generated coefficients from our developed algorithms are referred to as Fourier Klobuchar model (FOKM) coefficients, while those coefficients from BRDC massages are named as BRDC coefficients. The correlation coefficient values between FOKM and BRDC were higher than 0.97. We estimated total electron content using the Klobuchar model with FOKM coefficients and compared the result with that from the BRDC model. As a result, the maximum root mean square was 1.6 total electron content unit.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1871-1874
• /
• 2003

Knowledge-based numeric open caption recognition is proposed that can recognize numeric captions generated by character generator (CG) and automatically superimpose a modified caption using the recognized text only when a valid numeric caption appears in the aimed specific region of a live sportscast scene produced by other broadcasting stations. in the proposed method, mesh features are extracted from an enhanced binary image as feature vectors, then a valuable information is recovered from a numeric image by perceiving the character using a multiplayer perceptron (MLP) network. The result is verified using knowledge-based hie set designed for a more stable and reliable output and then the modified information is displayed on a screen by CG. MLB Eye Caption based on the proposed algorithm has already been used for regular Major League Base-ball (MLB) programs broadcast five over a Korean nationwide TV network and has produced a favorable response from Korean viewer.